© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11129
    Prev
    Next
    INDEX
    Explanations

    code regeneration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÜR
    -1.10
     chinois
    -1.05
    Racing
    -1.03
     ciclismo
    -0.98
     tremp
    -0.98
    Ќ
    -0.97
     annoncé
    -0.97
     pouvons
    -0.95
    ётся
    -0.94
     spé
    -0.93
    POSITIVE LOGITS
     again
    1.63
     continued
    1.28
     this
    1.23
     from
    1.22
     or
    1.18
     will
    1.16
     kunjungan
    1.16
     erne
    1.11
     generated
    1.10
     volverá
    1.08
    Activations Density 0.013%

    No Known Activations